{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DZWJHIUS7KDGE6VX4E7OLER6YY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a540233e7a581b419ef57423b15de8382571e56a974528fd8f7c027123f8f5c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-08T01:45:01Z","title_canon_sha256":"e15071710626e996623049a8764f73eaf7fde70eeff1eecb7cd7bdf4d48d879b"},"schema_version":"1.0","source":{"id":"2602.07764","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07764","created_at":"2026-07-13T01:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07764v2","created_at":"2026-07-13T01:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07764","created_at":"2026-07-13T01:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"DZWJHIUS7KDG","created_at":"2026-07-13T01:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"DZWJHIUS7KDGE6VX","created_at":"2026-07-13T01:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"DZWJHIUS","created_at":"2026-07-13T01:17:56Z"}],"graph_snapshots":[{"event_id":"sha256:e0c611ff9c5db56fd9a615e592ca1e9ec7783ff186254f5dced1b7fa9b64f782","target":"graph","created_at":"2026-07-13T01:17:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.07764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-objective reinforcement learning (MORL) seeks to train agents capable of balancing conflicting objectives. While single preference-conditioned policies offer a highly scalable solution, existing approaches remain brittle in practice, frequently failing to recover dense Pareto fronts. We demonstrate that this failure stems from two structural pathologies: destructive advantage cancellation caused by premature Early Scalarization (ES), and representational mode collapse across the preference space. To overcome these bottlenecks, we introduce $D^3PO$, a PPO-based framework that fundamentall","authors_text":"Abhinav Verma, Jonathan Dodge, Shreyash Kale, Sourav Panda, Tanmay Ambadkar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-08T01:45:01Z","title":"Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07764","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac365bd8b35047a249ee5172a4a00cfc55af9bb8d6da348b99072270cbda567e","target":"record","created_at":"2026-07-13T01:17:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a540233e7a581b419ef57423b15de8382571e56a974528fd8f7c027123f8f5c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-08T01:45:01Z","title_canon_sha256":"e15071710626e996623049a8764f73eaf7fde70eeff1eecb7cd7bdf4d48d879b"},"schema_version":"1.0","source":{"id":"2602.07764","kind":"arxiv","version":2}},"canonical_sha256":"1e6c93a292fa86627ab7e13ee5923ec632d76e78b803ec3082fc876f12179ffc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e6c93a292fa86627ab7e13ee5923ec632d76e78b803ec3082fc876f12179ffc","first_computed_at":"2026-07-13T01:17:56.816822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:17:56.816822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VaA2+WgCl2gmiyjwwmYcXrCp17lCvehXRnQtPTZfeCr4UvZ3NkdTVSfbmsb1gJqnReKAZouFT8TdvCI5elfqBQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:17:56.818812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07764","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac365bd8b35047a249ee5172a4a00cfc55af9bb8d6da348b99072270cbda567e","sha256:e0c611ff9c5db56fd9a615e592ca1e9ec7783ff186254f5dced1b7fa9b64f782"],"state_sha256":"9dbdca475142e8101b0014303e5291c88e009b7217c3f8c3879202355f738c23"}